pendulum-sac-tf:
    env: Pendulum-v0
    run: SAC
    stop:
        episode_reward_mean: -300  # note that evaluation perf is higher
        timesteps_total: 10000
    config:
        use_pytorch: false
        soft_horizon: true
        clip_actions: false
        normalize_actions: true
        metrics_smoothing_episodes: 5
        no_done_at_end: true